Application of LSTM Network to Improve Indoor Positioning Accuracy

Gao, Dongqi; Zeng, Xiangye; Wang, Jingyi; Su, Yanmang

doi:10.3390/s20205824

Cited by 12 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the research on UWB positioning was only conducted theoretically based on simulation experiments, and there was no verification in practical applications. Gao et al proposed using the LSTM network to predict the ranging error between the anchor point and the target, and they combined weighted least squares and regression weighted least squares for positioning correction, which improved UWB positioning accuracy 24 . However, their study did not take other deep learning algorithms for comparison and did not analyze the limitations and advantages of the LSTM algorithm in UWB indoor positioning systems.…”

Section: Introductionmentioning

confidence: 99%

Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioning

Tian,

Lian,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Ultra-wideband technology has good anti-interference capabilities and development prospects in indoor positioning. Since ultra-wideband will be affected by random errors in indoor positioning, to exploit the advantages of the Kalman filter (KF) and the long short-term memory (LSTM) network, this paper proposes a long short-term memory neural network algorithm fused with the Kalman filter (KF–LSTM) to improve UWB positioning. First, the ultra-wideband data is processed through KF to weaken the noise in the data, and then the data is fed into the LSTM network for training, and the capability of the LSTM network to process time series features is employed to obtain more accurate label positions. Finally, simulation and measurement results show that the KF–LSTM algorithm achieves 71.31%, 37.28%, and 49.31% higher average positioning accuracy than the back propagation (BP) network, (back propagation network fused with the Kalman filter (KF-BP), and LSTM network algorithms, respectively, and the KF–LSTM algorithm performs more stably. Meanwhile, the more noise the data contains, the more obvious the stability contrast between the four algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioning

Tian,

Lian,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Apart from traditional methods, machine learning methods are also used to increase the accuracy of determined positions. Their use is not always directly related to the object position, e.g., fingerprinting [49,50], but they have an impact on it, e.g., by detecting LOS/non-line-of-sight (NLOS) conditions [51][52][53] or even LOS/NLOS/multi-path (MP) conditions [54] or system error prediction [55,56]. In [57], the authors proposed the use of an LSTM network to determine the position of an object based on distances to 3 reference nodes.…”

Section: Introductionmentioning

confidence: 99%

Using the LSTM Neural Network and the UWB Positioning System to Predict the Position of Low and High Speed Moving Objects

Paszek,

Grzechca

2023

Sensors

View full text Add to dashboard Cite

Automation of transportation will play a crucial role in the future when people driving vehicles will be replaced by autonomous systems. Currently, the positioning systems are not used alone but are combined in order to create cooperative positioning systems. The ultra-wideband (UWB) system is an excellent alternative to the global positioning system (GPS) in a limited area but has some drawbacks. Despite many advantages of various object positioning systems, none is free from the problem of object displacement during measurement (data acquisition), which affects positioning accuracy. In addition, temporarily missing data from the absolute positioning system can lead to dangerous situations. Moreover, data pre-processing is unavoidable and takes some time, affecting additionally the object’s displacement in relation to its previous position and its starting point of the new positioning process. So, the prediction of the position of an object is necessary to minimize the time when the position is unknown or out of date, especially when the object is moving at high speed and the position update rate is low. This article proposes using the long short-term memory (LSTM) artificial neural network to predict objects’ positions based on historical data from the UWB system and inertial navigation. The proposed solution creates a reliable positioning system that predicts 10 positions of low and high-speed moving objects with an error below 10 cm. Position prediction allows detection of possible collisions—the intersection of the trajectories of moving objects.

show abstract

TTSL: An indoor localization method based on Temporal Convolutional Network using time-series RSSI

Jia

Liu

Feng

et al. 2022

Computer Communications

View full text Add to dashboard Cite

Application of LSTM Network to Improve Indoor Positioning Accuracy

Cited by 12 publications

References 22 publications

Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioning

Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioning

Using the LSTM Neural Network and the UWB Positioning System to Predict the Position of Low and High Speed Moving Objects

TTSL: An indoor localization method based on Temporal Convolutional Network using time-series RSSI

Contact Info

Product

Resources

About